Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal characteristics, actions, and beliefs

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.14
     kasarigan
    -0.64
     ivelany
    -0.58
    Referencie
    -0.58
    tagHelperRunner
    -0.57
    Atsauces
    -0.57
    UnusedPrivate
    -0.55
    Enllaços
    -0.55
    Viited
    -0.54
     كومونز
    -0.52
    POSITIVE LOGITS
     ananas
    0.65
     porc
    0.64
     pican
    0.64
     posX
    0.62
    richText
    0.61
     marte
    0.60
     zucca
    0.60
     maroc
    0.59
     moza
    0.58
     tenda
    0.58
    Act Density 2.516%

    No Known Activations